Nicodemus Naisau, . (2024) ANALISIS SENTIMENT PENGGUNA APLIKASI TROVESKIN BERDASARKAN ULASAN PADA GOOGLE PLAY STORE MENGGUNAKAN METODE NAÏVE BAYES ALGORITHM. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (7kB) |
|
Text
AWAL.pdf Download (907kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (617kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (4MB) |
|
Text
BAB 5.pdf Download (217kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (510kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (85kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (6MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (7MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (1MB) |
Abstract
TroveSkin is a beauty care usage tracking application, and this research aims to analyze user sentiments regarding the TroveSkin app, focusing on the quality of performance and services offered. The research methodology involves the use of the Naïve Bayes algorithm to analyze sentiments from 3000 user reviews on the Google Play Store. Review data is manually labeled based on rating scores to classify them as positive or negative. The results of sentiment analysis are utilized to create a visualized dashboard, providing a clear overview of user preferences and satisfaction with TroveSkin's performance and services. The research findings indicate that user sentiments lean towards the positive, reflecting current satisfaction with the app's services. The Naïve Bayes classification model applied to review data achieves an accuracy of 80%, with precision at 82% and recall at 81%. This research has a significant impact on understanding user preferences regarding TroveSkin's features, services, and performance. Recommendations based on positive reviews include expanding skin detection features, improving the quality of product recommendations, diversifying products, providing richer educational content, and introducing skin progress tracking features. On the other hand, negative reviews highlight the need for improvements in the app's performance, responsiveness to user feedback, accuracy of product recommendations, clarity of instructions, and considerations for user privacy.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010512062] [Pembimbing 1: Widya Cholil] [Pembimbing 2: Erly Krisnanik] [Penguji 1: Ermatita] [Penguji 2: Nindy Irzavika] |
| Uncontrolled Keywords: | Data Mining, Sentiment Analysis, Naïve Bayes, Dashboard. |
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Sistem Informasi (S1) |
| Depositing User: | Nicodemus Naisau |
| Date Deposited: | 19 Feb 2024 03:39 |
| Last Modified: | 19 Feb 2024 03:39 |
| URI: | http://repository.upnvj.ac.id/id/eprint/28866 |
Actions (login required)
 |
View Item |